Class GateExitTwoOp

Provides outgoing messages for ExitTwo<T>(Boolean, Boolean, T[]), given random arguments to the function.

Inheritance

Object

GateExitTwoOp

Inherited Members

Object.Equals(Object)

Object.Equals(Object, Object)

Object.GetHashCode()

Object.GetType()

Object.MemberwiseClone()

Object.ReferenceEquals(Object, Object)

Object.ToString()

Namespace: Microsoft.ML.Probabilistic.Factors

Assembly: Microsoft.ML.Probabilistic.dll

Syntax

[FactorMethod(typeof(Gate), "ExitTwo<>", new Type[]{})]
[Quality(QualityBand.Mature)]
public static class GateExitTwoOp

Methods

AverageLogFactor<TExit>(TExit, Bernoulli, Bernoulli, IList<TExit>, TExit)

Evidence message for VMP.

Declaration

public static double AverageLogFactor<TExit>(TExit exitTwo, Bernoulli case0, Bernoulli case1, IList<TExit> values, TExit to_exitTwo)
    where TExit : ICloneable, SettableToProduct<TExit>, SettableToPower<TExit>, CanGetAverageLog<TExit>, SettableToUniform, SettableTo<TExit>, SettableToRatio<TExit>, SettableToWeightedSum<TExit>

Parameters

Type	Name	Description
TExit	exitTwo	Incoming message from exitTwo.
Bernoulli	case0	Incoming message from case0.
Bernoulli	case1	Incoming message from case1.
IList<TExit>	values	Incoming message from values.
TExit	to_exitTwo	Outgoing message to exitTwo.

Returns

Type	Description
Double	Zero.

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.

Remarks

In Variational Message Passing, the evidence contribution of a deterministic factor is zero. Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

Case0AverageConditional<TExit>(IList<TExit>)

EP message to case0.

Declaration

public static Bernoulli Case0AverageConditional<TExit>([SkipIfAllUniform] IList<TExit> values)

Parameters

Type	Name	Description
IList<TExit>	values	Incoming message from values. Must be a proper distribution. If all elements are uniform, the result will be uniform.

Returns

Type	Description
Bernoulli	The outgoing EP message to the case0 argument.

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.

Remarks

The outgoing message is a distribution matching the moments of case0 as the random arguments are varied. The formula is proj[p(case0) sum_(values) p(values) factor(exitTwo,case0,case1,values)]/p(case0).

Exceptions

Type	Condition
ImproperMessageException	values is not a proper distribution.

Case0AverageConditional<TExit, TExitDomain>(TExit, IList<TExitDomain>)

EP message to case0.

Declaration

public static Bernoulli Case0AverageConditional<TExit, TExitDomain>(TExit exitTwo, IList<TExitDomain> values)
    where TExit : CanGetLogProb<TExitDomain>

Parameters

Type	Name	Description
TExit	exitTwo	Incoming message from exitTwo.
IList<TExitDomain>	values	Incoming message from values.

Returns

Type	Description
Bernoulli	The outgoing EP message to the case0 argument.

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.
TExitDomain	The domain of the variable exiting the gate.

Remarks

The outgoing message is a distribution matching the moments of case0 as the random arguments are varied. The formula is proj[p(case0) sum_(exitTwo,values) p(exitTwo,values) factor(exitTwo,case0,case1,values)]/p(case0).

Case0AverageLogarithm<TExit>(TExit, IList<TExit>)

VMP message to case0.

Declaration

public static Bernoulli Case0AverageLogarithm<TExit>(TExit exitTwo, [SkipIfAllUniform] IList<TExit> values)
    where TExit : CanGetAverageLog<TExit>

Parameters

Type	Name	Description
TExit	exitTwo	Incoming message from exitTwo.
IList<TExit>	values	Incoming message from values. Must be a proper distribution. If any element is uniform, the result will be uniform.

Returns

Type	Description
Bernoulli	The outgoing VMP message to the case0 argument.

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.

Remarks

The outgoing message is the exponential of the average log-factor value, where the average is over all arguments except case0. Because the factor is deterministic, exitTwo is integrated out before taking the logarithm. The formula is exp(sum_(values) p(values) log(sum_exitTwo p(exitTwo) factor(exitTwo,case0,case1,values))).

Exceptions

Type	Condition
ImproperMessageException	values is not a proper distribution.

Case1AverageConditional<TExit>(IList<TExit>)

EP message to case1.

Declaration

public static Bernoulli Case1AverageConditional<TExit>([SkipIfAllUniform] IList<TExit> values)

Parameters

Type	Name	Description
IList<TExit>	values	Incoming message from values. Must be a proper distribution. If all elements are uniform, the result will be uniform.

Returns

Type	Description
Bernoulli	The outgoing EP message to the case1 argument.

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.

Remarks

The outgoing message is a distribution matching the moments of case1 as the random arguments are varied. The formula is proj[p(case1) sum_(values) p(values) factor(exitTwo,case0,case1,values)]/p(case1).

Exceptions

Type	Condition
ImproperMessageException	values is not a proper distribution.

Case1AverageConditional<TExit, TExitDomain>(TExit, IList<TExitDomain>)

EP message to case1.

Declaration

public static Bernoulli Case1AverageConditional<TExit, TExitDomain>(TExit exitTwo, IList<TExitDomain> values)
    where TExit : CanGetLogProb<TExitDomain>

Parameters

Type	Name	Description
TExit	exitTwo	Incoming message from exitTwo.
IList<TExitDomain>	values	Incoming message from values.

Returns

Type	Description
Bernoulli	The outgoing EP message to the case1 argument.

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.
TExitDomain	The domain of the variable exiting the gate.

Remarks

The outgoing message is a distribution matching the moments of case1 as the random arguments are varied. The formula is proj[p(case1) sum_(exitTwo,values) p(exitTwo,values) factor(exitTwo,case0,case1,values)]/p(case1).

Case1AverageLogarithm<TExit>(TExit, IList<TExit>)

VMP message to case1.

Declaration

public static Bernoulli Case1AverageLogarithm<TExit>(TExit exitTwo, [SkipIfAllUniform] IList<TExit> values)
    where TExit : CanGetAverageLog<TExit>

Parameters

Type	Name	Description
TExit	exitTwo	Incoming message from exitTwo.
IList<TExit>	values	Incoming message from values. Must be a proper distribution. If any element is uniform, the result will be uniform.

Returns

Type	Description
Bernoulli	The outgoing VMP message to the case1 argument.

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.

Remarks

The outgoing message is the exponential of the average log-factor value, where the average is over all arguments except case1. Because the factor is deterministic, exitTwo is integrated out before taking the logarithm. The formula is exp(sum_(values) p(values) log(sum_exitTwo p(exitTwo) factor(exitTwo,case0,case1,values))).

Exceptions

Type	Condition
ImproperMessageException	values is not a proper distribution.

ExitTwoAverageConditional<TExit>(TExit, Bernoulli, Bernoulli, IList<TExit>, TExit)

EP message to exitTwo.

Declaration

public static TExit ExitTwoAverageConditional<TExit>(TExit exitTwo, Bernoulli case0, Bernoulli case1, [SkipIfAllUniform] IList<TExit> values, TExit result)
    where TExit : SettableTo<TExit>, ICloneable, SettableToProduct<TExit>, SettableToRatio<TExit>, SettableToWeightedSum<TExit>

Parameters

Type	Name	Description
TExit	exitTwo	Incoming message from exitTwo.
Bernoulli	case0	Incoming message from case0.
Bernoulli	case1	Incoming message from case1.
IList<TExit>	values	Incoming message from values. Must be a proper distribution. If all elements are uniform, the result will be uniform.
TExit	result	Modified to contain the outgoing message.

Returns

Type	Description
TExit	result

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.

Remarks

The outgoing message is a distribution matching the moments of exitTwo as the random arguments are varied. The formula is proj[p(exitTwo) sum_(case0,case1,values) p(case0,case1,values) factor(exitTwo,case0,case1,values)]/p(exitTwo).

Exceptions

Type	Condition
ImproperMessageException	values is not a proper distribution.

ExitTwoAverageConditional<TExit, TExitDomain>(TExit, Bernoulli, Bernoulli, IList<TExitDomain>, TExit)

EP message to exitTwo.

Declaration

public static TExit ExitTwoAverageConditional<TExit, TExitDomain>(TExit exitTwo, Bernoulli case0, Bernoulli case1, IList<TExitDomain> values, TExit result)
    where TExit : ICloneable, HasPoint<TExitDomain>, SettableToWeightedSum<TExit>

Parameters

Type	Name	Description
TExit	exitTwo	Incoming message from exitTwo.
Bernoulli	case0	Incoming message from case0.
Bernoulli	case1	Incoming message from case1.
IList<TExitDomain>	values	Incoming message from values.
TExit	result	Modified to contain the outgoing message.

Returns

Type	Description
TExit	result

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.
TExitDomain	The domain of the variable exiting the gate.

Remarks

The outgoing message is a distribution matching the moments of exitTwo as the random arguments are varied. The formula is proj[p(exitTwo) sum_(case0,case1,values) p(case0,case1,values) factor(exitTwo,case0,case1,values)]/p(exitTwo).

ExitTwoAverageLogarithm<TExit>(Bernoulli, Bernoulli, IList<TExit>, TExit)

VMP message to exitTwo.

Declaration

public static TExit ExitTwoAverageLogarithm<TExit>(Bernoulli case0, Bernoulli case1, [SkipIfAllUniform] IList<TExit> values, TExit result)
    where TExit : ICloneable, SettableToProduct<TExit>, SettableToPower<TExit>, CanGetAverageLog<TExit>, SettableToUniform, SettableTo<TExit>, SettableToRatio<TExit>, SettableToWeightedSum<TExit>

Parameters

Type	Name	Description
Bernoulli	case0	Incoming message from case0.
Bernoulli	case1	Incoming message from case1.
IList<TExit>	values	Incoming message from values. Must be a proper distribution. If any element is uniform, the result will be uniform.
TExit	result	Modified to contain the outgoing message.

Returns

Type	Description
TExit	result

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.

Remarks

The outgoing message is a distribution matching the moments of exitTwo as the random arguments are varied. The formula is proj[sum_(case0,case1,values) p(case0,case1,values) factor(exitTwo,case0,case1,values)].

Exceptions

Type	Condition
ImproperMessageException	values is not a proper distribution.

ValuesAverageConditional<TExit, TResultList>(TExit, TResultList)

EP message to values.

Declaration

public static TResultList ValuesAverageConditional<TExit, TResultList>(TExit exitTwo, TResultList result)
    where TResultList : CanSetAllElementsTo<TExit>

Parameters

Type	Name	Description
TExit	exitTwo	Incoming message from exitTwo. Must be a proper distribution. If uniform, the result will be uniform.
TResultList	result	Modified to contain the outgoing message.

Returns

Type	Description
TResultList	result

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.
TResultList	The type of the outgoing message.

Remarks

The outgoing message is a distribution matching the moments of values as the random arguments are varied. The formula is proj[p(values) sum_(exitTwo) p(exitTwo) factor(exitTwo,case0,case1,values)]/p(values).

Exceptions

Type	Condition
ImproperMessageException	exitTwo is not a proper distribution.

ValuesAverageLogarithm<TExit, TResultList>(TExit, TResultList)

VMP message to values.

Declaration

public static TResultList ValuesAverageLogarithm<TExit, TResultList>(TExit exitTwo, TResultList result)
    where TResultList : CanSetAllElementsTo<TExit>

Parameters

Type	Name	Description
TExit	exitTwo	Incoming message from exitTwo. Must be a proper distribution. If uniform, the result will be uniform.
TResultList	result	Modified to contain the outgoing message.

Returns

Type	Description
TResultList	result

Type Parameters

Name	Description
TExit	The type of the distribution over the variable exiting the gate.
TResultList	The type of the outgoing message.

Remarks

The outgoing message is the factor viewed as a function of values with exitTwo integrated out. The formula is sum_exitTwo p(exitTwo) factor(exitTwo,case0,case1,values).

Exceptions

Type	Condition
ImproperMessageException	exitTwo is not a proper distribution.